Machine learning diabetic retinopathy onset risk prediction method and application

A technology of diabetic retina and machine learning, applied in the fields of instrumentation, informatics, medical informatics, etc., can solve the problems of inconsistent standards, low predictive ability of simple prediction models, and low risk prediction efficiency.

Inactive Publication Date: 2021-05-11
TIANJIN MEDICAL UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention overcomes the problems of low efficiency of risk prediction for medical personnel, non-uniform standards, subjective differ

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Machine learning diabetic retinopathy onset risk prediction method and application

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 1As shown, the present invention provides a diabetic retinopathy risk prediction model based on machine learning and metabolic features. The method includes: performing metabolomics detection on the blood samples of the population to be predicted, and obtaining metabolomics characteristic data; preprocessing the collected raw data, using a random forest model to fill in missing values, and performing normalization and discretization on the data Processing; use the preprocessed data to predict using a model based on random forest and support vector machine, and output the prediction result. If the output result is 1, there is a risk of diabetic retinopathy, and if the output result is 0, it does not exist risk of diabetic retinopathy.

[0039] As mentioned above, the embodiments of the present invention provide a method for predicting the risk of diabetic retinopathy based on machine learning algorithms and metabolic characteristics, using techniques main...

Embodiment 2

[0041] See figure 1 , after a patient draws blood in the hospital, the blood sample is analyzed by the staff using a high-throughput analysis instrument to obtain amino acid and carnitine data; the staff fills in the amino acid carnitine data into the preprocessing module and runs the preprocessing program; the preprocessing Put the final data into the model and run the prediction program; output the prediction result. The prediction result of the model is 1 for the metabolic data of a patient, indicating that he has a risk of diabetic retinopathy.

Embodiment 3

[0043] After a subject obtains a metabolic analysis report from a company, he submits the report to the staff, and the staff uses the preprocessing module to preprocess and analyze the data according to the test results. The preprocessed data is used to make predictions using the model. If the result of the prediction output is 0, the subject has no risk of diabetic retinopathy.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a machine learning diabetic retinopathy onset risk prediction method. The method comprises the following steps: a data acquisition module for acquiring metabonomics data; a data preprocessing module for preprocessing the acquired data; a machine learning module for constructing a prediction model based on a machine learning algorithm and metabonomics data in order to predict the risk of diabetic retinopathy; a display output module for testing the obtained to-be-predicted sample and outputting a prediction result, wherein if the prediction result is 1, the diabetic retinopathy risk exists, and if the prediction result is 0, the diabetic retinopathy risk does not exist. By applying the embodiment of the invention, the diabetic retinopathy risk prediction model is constructed by combining metabonomics characteristics on the basis of technologies mainly based on the random forest and the support vector machine algorithm. The method can be used for improving decision-making efficiency, guiding non-medical personnel to carry out disease risk detection or assisting clinical decision-making, and achieving the purposes of three-level prevention of diseases and promotion and development of health of the whole people.

Description

technical field [0001] The invention belongs to a method for constructing a model by using a machine learning algorithm and using a novel predictor to predict the risk of diabetic retinopathy. Background technique [0002] Disease risk prediction is mainly used to assist clinical decision-making, health detection of sensitive groups, and disease risk detection for non-medical personnel. [0003] Diabetes mellitus is a group of metabolic diseases characterized by hyperglycemia and caused by multiple etiologies. Diabetic retinopathy is one of the most common microvascular complications of diabetic patients, and it is also the main cause of blindness in patients, which increases the disease and economic burden of individuals and society. [0004] At present, the prediction of the risk of diabetic retinopathy mainly includes relying on the professional knowledge of medical staff or using simple prediction models constructed by traditional risk factors. Judging diseases through...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G16H50/30G16H50/70G16H15/00G06K9/62
CPCG16H50/30G16H50/70G16H15/00G06F18/2411G06F18/24323
Inventor 房中则刘永哲高小茜王婉莹李欣
Owner TIANJIN MEDICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap